Skip to main content
POST
/
generate
/
vol
/
seedance-2.0
Seedance 2.0 Video Generation
curl --request POST \
  --url https://api.sinancode.com/v1/generate/vol/seedance-2.0 \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "reference_images": [
    "<string>"
  ],
  "duration": 5,
  "first_frame": "https://example.com/first_frame.jpg",
  "generate_audio": true,
  "last_frame": "https://example.com/last_frame.jpg",
  "model": "fast",
  "prompt": "女孩抱着狐狸，女孩睁开眼，温柔地看向镜头",
  "ratio": "adaptive",
  "resolution": "720p",
  "watermark": false
}
'
{
  "task_id": "01234567-89ab-cdef-0123-456789abcdef"
}
Generate videos using Volcano Engine’s Seedance 2.0 model. Key Features:
  • Multiple Generation Modes - Text-to-video, image-to-video (first frame / first+last frame), and multi-modal reference-to-video
  • Audio Generation - Built-in audio generation support
  • Fast & Standard Modes - Choose between 2.0 Fast (faster, cheaper) and 2.0 Standard
  • Flexible Duration - 4-15 seconds, or let the model decide automatically

Authorizations

​
Authorization
string
header
required

Please use your API Token for authentication

Body

application/json

Task parameters

​
reference_images
string[]
required

Reference image URL list (optional, 1-9 images, for multimodal reference-to-video) Note: reference images and first/last frame modes are mutually exclusive

Maximum array length: 9
​
duration
integer
default:5

Video duration (optional, default 5 seconds) Range: 4-15 seconds, or set to -1 for automatic selection

Required range: -1 <= x <= 15
Example:

5

​
first_frame
string

First frame image URL (optional, for image-to-video first frame mode)

Example:

"https://example.com/first_frame.jpg"

​
generate_audio
boolean
default:true

Whether to generate audio (optional, default true)

Example:

true

​
last_frame
string

Last frame image URL (optional, must be used together with first_frame)

Example:

"https://example.com/last_frame.jpg"

​
model
enum<string>
default:fast

Model version (optional, default fast) Options: fast (2.0 Fast, faster and cheaper), standard (2.0 Standard)

Available options:
fast,
standard
Example:

"fast"

​
prompt
string

Prompt (optional, can be omitted for multimodal reference mode)

Maximum string length: 2000
Example:

"女孩抱着狐狸，女孩睁开眼，温柔地看向镜头"

​
ratio
enum<string>
default:adaptive

Aspect ratio (optional, default adaptive)

Available options:
16:9,
4:3,
1:1,
3:4,
9:16,
21:9,
adaptive
Example:

"adaptive"

​
resolution
enum<string>
default:720p

Resolution (optional, default 720p) Seedance 2.0 does not support 1080p

Available options:
480p,
720p
Example:

"720p"

​
watermark
boolean
default:false

Whether to add watermark (optional, default false)

Example:

false

Response

OK

​
task_id
string
required

Task ID

Example:

"01234567-89ab-cdef-0123-456789abcdef"